Everything you need to go from idea to video
Four AI studios and a motion editor that work as one product.
Image
Campaign-ready images from a sentence, with the leading image models in one place.
- Six image models, from fast drafts to premium detail
- Reference images to keep your product and style consistent
- 16:9, 9:16, 1:1, 4:3 and 3:4 formats
- Send any result straight to the motion editor
Video
Turn text or a still image into video with Veo, Kling, Seedance, Wan, Runway and Hailuo.
- Ten video models with clear per-clip pricing
- Text to video and image to video
- First and last frame control on supported models
- Vertical, square and landscape output
Avatar
Upload a photo, write a script and get a lip-synced presenter, without a camera.
- One photo and a script are enough
- Multilingual and language-specific voices
- 16:9, 9:16 and 1:1 output
- Consent confirmation; public figures are not allowed
Voice
Natural voiceovers for ads and videos, ready for your timeline in seconds.
- ElevenLabs multilingual and turbo models
- A text-to-speech draft for just a few credits
- MP3 output you can download
- Transcription for captions at 1 credit per minute
Motion editor
Finish your AI clips where you made them, with titles, captions and animation.
- Video, image, audio, text and shape layers
- Motion templates: title, lower third, logo reveal, kinetic text, CTA, transition
- Keyframes for position, scale, rotation and opacity
- Describe a motion graphic and AI fills in the template